Unverified50% confidenceFactExact time
Post-hoc explanation methods include SHAP and LIME, and intrinsic interpretable models include linear models and decision trees.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSHAP and LIME are both post-hoc explanation frameworks that do not modify the model itself, but instead generate explanations after predictions are made.76% similarUnverifiedLIME explains individual predictions by generating a perturbed dataset around the input sample to train a local linear approximation model, while SHAP provides feature attribution based on game-theoretic Shapley values; both are model-agnostic techniques.73% similarUnverifiedSHAP的核心思想是将每个特征对模型预测的贡献量化，使得所有特征贡献之和等于模型预测值与基线值的差73% similarUnverified可说明性（Explainability）催生了LIME、SHAP等事后归因方法，面向外部用户回答为什么模型给出该输出73% similarVerifiedLIME (Local Interpretable Model-Agnostic Explanations) and SHAP (SHapley Additive exPlanations) are the primary tools for providing post-hoc explanations for complex black-box models.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1101309API
curl https://kongchang.com/api/v1/knowledge/claims/1101309MCP
get_claim(id=1101309)